ML Security Insights
Models are likely to remain susceptible to simple attacks for the foreseeable future, necessitating the design of systems that can operate securely despite these vulnerabilities. Decisions around ML security should be grounded in reality rather than idealistic views, ensuring that actions taken in response to model failures are well-considered and safe. The challenge lies in creating robust systems that can mitigate the risks posed by unreliable models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Nicholas Carlini (Google DeepMind)
Related Questions